I wrote this morning’s column partly because I had a hunch that the Obama people might be thinking too small on stimulus. Now I have more than a hunch – I’ve heard an unreliable rumor! So let’s talk about stimulus math, as I see it.

Actually, before I get to the math, some concepts. Nearly every forecast now says that, in the absence of strong policy action, real GDP will fall far below potential output in the near future. In normal times, that would be a reason to cut interest rates. But interest rates can’t be cut in any meaningful sense. Fiscal policy is the only game in town.

Wait, there’s more. Ben Bernanke can’t push on a string – but he can pull, if necessary. Suppose fiscal policy ends up being too expansionary, so that real GDP “wants” to come in 2 percent above potential. In that case the Fed can tighten a bit, and no harm is done. But if fiscal policy is too contractionary, and real GDP comes in below potential, there’s no potential monetary offset. That means that fiscal policy should take risks in the direction of boldness.

So what kinds of numbers are we talking about? GDP next year will be about $15 trillion, so 1% of GDP is $150 billion. The natural rate of unemployment is, say, 5% — maybe lower. Given Okun’s law, every excess point of unemployment above 5 means a 2% output gap.

Right now, we’re at 6.5% unemployment and a 3% output gap – but those numbers are heading higher fast. Goldman predicts 8.5% unemployment, meaning a 7% output gap. That sounds reasonable to me.

So we need a fiscal stimulus big enough to close a 7% output gap. Remember, if the stimulus is too big, it does much less harm than if it’s too small. What’s the multiplier? Better, we hope, than on the early-2008 package. But you’d be hard pressed to argue for an overall multiplier as high as 2.

When I put all this together, I conclude that the stimulus package should be at least 4% of GDP, or $600 billion.

That’s twice what the unreliable rumor says. So if there’s any truth to the rumor, my advice to the powers that be (or more accurately will be in a couple of months) is to think hard – you really, really don’t want to lowball this.